Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis ...

This paper investigates the use of unsupervised text-to-speech synthesis (TTS) as a data augmentation method to improve accented speech recognition. TTS systems are trained with a small amount of accented speech training data and their pseudo-labels rather than manual transcriptions, and hence unsup...

Full description

Bibliographic Details
Main Authors: Do, Cong-Thanh, Imai, Shuhei, Doddipatla, Rama, Hain, Thomas
Format: Report
Language:unknown
Published: arXiv 2024
Subjects:
Computation and Language cs.CL
Sound cs.SD
Audio and Speech Processing eess.AS
FOS Computer and information sciences
FOS Electrical engineering, electronic engineering, information engineering
Arctic
Online Access:https://dx.doi.org/10.48550/arxiv.2407.04047
https://arxiv.org/abs/2407.04047
Description
Summary:This paper investigates the use of unsupervised text-to-speech synthesis (TTS) as a data augmentation method to improve accented speech recognition. TTS systems are trained with a small amount of accented speech training data and their pseudo-labels rather than manual transcriptions, and hence unsupervised. This approach enables the use of accented speech data without manual transcriptions to perform data augmentation for accented speech recognition. Synthetic accented speech data, generated from text prompts by using the TTS systems, are then combined with available non-accented speech data to train automatic speech recognition (ASR) systems. ASR experiments are performed in a self-supervised learning framework using a Wav2vec2.0 model which was pre-trained on large amount of unsupervised accented speech data. The accented speech data for training the unsupervised TTS are read speech, selected from L2-ARCTIC and British Isles corpora, while spontaneous conversational speech from the Edinburgh international ... : Accepted to EUSIPCO 2024 ...

Similar Items